Model Detail
sweep-next-edit-v2-7B
—sweep-next-edit-v2-7B is a code generation model with 7B parameters released by sweepai. The model is registered under the text-generation pipeline tag on Hugging Face, distributed under the permissive apache-2.0 license.
sweep-next-edit-v2-7B ships with 7B parameters. Total weight footprint is approximately 7.6 GB, which is the relevant figure when planning local-inference VRAM. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
sweep-next-edit-v2-7B is best fit for code completion, repository-scale Q&A, and pair-programming integrations. It is a less obvious choice for one-shot generation of security-critical code without review. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Dense Mixture-of-Experts as a Reparameterized Wide FFN: A Granularity Sweep at Fixed Compute
arXiv:2610.02584v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models combine learned routing with selection from a large expert pool. We isolate the contribution of dynamic expert combination using a dense analogue: $K$ SwiGLU experts, all active for every token and combined by a s
Echo State Networks for Time Series Forecasting: Hyperparameter Sweep and Benchmarking
arXiv:2602.03912v5 Announce Type: replace Abstract: This paper investigates the performance of Echo State Networks (ESNs) for univariate forecasting of monthly and quarterly time series from the M4 Forecasting Competition dataset. We evaluate whether a simple first-order autoregressive ESN can serve
Accelerated Random-Sweep Gibbs Sampling for Gaussian Graphical Models via Dual Normal Factor Graphs
arXiv:2607.28706v1 Announce Type: cross Abstract: We study the convergence properties of the random-sweep Gibbs sampler for Gaussian graphical models with a thin-membrane prior. We demonstrate that the convergence rate of the Gibbs sampler is significantly accelerated in the dual model, which is obt
